홈 › Papers

A Prototypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot Name Entity Recognition

2023-02-27 · Guanting Dong, Zechen Wang, LiWen Wang, Daichi Guo, Dayuan Fu, Yuxiang Wu, Chen Zeng, Xuefeng Li, Tingfeng Hui, Keqing He, Xinyue Cui, QiXiang Gao, Weiran Xu

Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances. Most existing prototype-based sequence labeling models tend to memorize entity mentions which would be easily confused by close prototypes. In this paper, we proposed a Prototypical Semantic Decoupling method via joint Contrastive learning (PSDC) for few-shot NER. Specifically, we decouple class-specific prototypes and contextual semantic prototypes by two masking strategies to lead the model to focus on two different semantic information for inference. Besides, we further introduce joint contrastive learning objectives to better integrate two kinds of decoupling information and prevent semantic collapse. Experimental results on two few-shot NER benchmarks demonstrate that PSDC consistently outperforms the previous SOTA methods in terms of overall performance. Extensive analysis further validates the effectiveness and generalization of PSDC.

📄 PDF Abstract BibTeX arXiv:2302.13610

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning few-shot-ner Few-shot NERnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection

2022-05-01 · ACL 2022 5 · Bin Liang, Qinglin Zhu, Xiang Li, Min Yang 외

Zero-shot stance detection (ZSSD) aims to detect the stance for an unseen target during the inference stage. In this paper, we propose a joint contrastive learning (JointCL) framework, which consists of stance contrastiv…

Contrastive Learning Stance Detection Zero-Shot Stance Detection

Contrastive Prototypical Network with Wasserstein Confidence Penalty

2022-10-21 · European Conference on Computer Vision 2022 10 · Haoqing Wang, Zhi-Hong Deng

Unsupervised few-shot learning aims to learn the inductive bias from unlabeled dataset for solving the novel few-shot tasks. The existing unsupervised few-shot learning models and the contrastive learning models follow a…

Contrastive Learning Few-Shot Learning Inductive Bias Unsupervised Few-Shot Image Classification+1

Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation

2021-11-09 · Hyeongjun Kwon, Somi Jeong, Sunok Kim, Kwanghoon Sohn

We address the problem of few-shot semantic segmentation (FSS), which aims to segment novel class objects in a target image with a few annotated samples. Though recent advances have been made by incorporating prototype-b…

Contrastive Learning Few-Shot Semantic Segmentation Metric Learning Semantic Segmentation

Bridge to Target Domain by Prototypical Contrastive Learning and Label Confusion: Re-explore Zero-Shot Learning for Slot Filling

2021-10-07 · EMNLP 2021 11 · LiWen Wang, Xuefeng Li, Jiachi Liu, Keqing He 외

Zero-shot cross-domain slot filling alleviates the data dependence in the case of data scarcity in the target domain, which has aroused extensive research. However, as most of the existing methods do not achieve effectiv…

Contrastive Learning slot-filling Slot Filling Transfer Learning+2

CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detection

2024-08-30 · Xuejing Li, Weijia Zhang, Chao Ma

Few-shot point cloud 3D object detection (FS3D) aims to identify and localise objects of novel classes from point clouds, using knowledge learnt from annotated base classes and novel classes with very few annotations. Th…

3D Object Detection object-detection Object Detection